© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29897
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    304
    +0.13
    0.7%
    348
    +0.12
    0.7%
    178
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.13
    0.02
    304
    +0.12
    0.02
    58
    +0.12
    0.02
    Negative Logits
    ?)
    -1.68
    ¦
    -1.67
    escap
    -1.64
    Ł
    -1.63
    ĺ
    -1.52
    Ĭ
    -1.48
    ©
    -1.48
    STEM
    -1.47
    Ĺ
    -1.47
    Ĥ
    -1.47
    POSITIVE LOGITS
    ings
    2.38
    hav
    2.13
    league
    2.09
    zier
    2.04
    endar
    2.02
    aways
    1.94
    haviour
    1.91
    arers
    1.83
    hdad
    1.83
    efs
    1.81
    Activations Density 0.009%

    No Known Activations